Default priors for Gaussian processes

Motivated by the statistical evaluation of complex computer models, we deal with the issue of objective prior specification for the parameters of Gaussian processes. In particular, we derive the Jeffreys-rule, independence Jeffreys and reference priors for this situation, and prove that the resulting posterior distributions are proper under a quite general set of conditions. A proper flat prior strategy, based on maximum likelihood estimates, is also considered, and all priors are then compared on the grounds of the frequentist properties of the ensuing Bayesian procedures. Computational issues are also addressed in the paper, and we illustrate the proposed solutions by means of an example taken from the field of complex computer model validation.

• Publication year

  2005

• Venue

  Annals of Statistics

• Publication date

  2005-04-01

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1214/009053604000001264arXiv math/0505603
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A Framework for Validation of Computer Models

  2007cited by this paper
• Testing for separability of spatial–temporal covariance functions

  2006cited by this paper
• The Design and Analysis of Computer Experiments

  2003cited by this paper
• Bayesian calibration of computer models

  2001cited by this paper
• Objective Bayesian Analysis of Spatially Correlated Data

  2001influential reference
• Predicting the output from a complex computer code when fast approximations are available

  2000cited by this paper
• Matrix Algebra From a Statistician's Perspective

  1998influential reference
• Design and analysis of computer experiments

  1998cited by this paper
• The Selection of Prior Distributions by Formal Rules

  1996cited by this paper
• Bayesian Data Analysis.

  1996cited by this paper
• Statistics for Spatial Data, Revised Edition.

  1994cited by this paper
• 5. Statistics for Spatial Data

  1993cited by this paper
• Statistics for Spatial Data.

  1992cited by this paper
• The multivariate normal distribution

  1989cited by this paper
• Reference Posterior Distributions for Bayesian Inference

  1979cited by this paper
• Bayesian inference for variance components using only error contrasts

  1974influential reference

• Random Fourier Features Based Gaussian Process Models for Stochastic Simulations

  2026cites this paper
• Efficient multi-fidelity Gaussian process regression for noisy outputs and non-nested experimental designs

  2025cites this paper
• Prior distributions for Gaussian processes in computer model emulation and calibration

  2025influential citation
• Variational inference for approximate objective priors using neural networks

  2025cites this paper
• Probabilistic surrogate modeling by Gaussian process: A review on recent insights in estimation and validation

  2024cites this paper
• The slice sampler and centrally symmetric distributions

  2024cites this paper
• Properly constrained reference priors decay rates for efficient and robust posterior inference

  2024cites this paper
• Default Priors for the Smoothness Parameter in Gaussian Matérn Random Fields

  2024cites this paper
• Bayes Linear Analysis for Statistical Modelling with Uncertain Inputs

  2023cites this paper
• Generalized mutual information and their reference prior under Csizar f-divergence

  2023cites this paper
• Deterministic Objective Bayesian Analysis for Spatial Models

  2023cites this paper
• Incorporating Subsampling into Bayesian Models for High-Dimensional Spatial Data

  2023cites this paper
• Objective Bayesian analysis for geostatistical Student-t processes

  2023cites this paper
• Inferring differential subcellular localisation in comparative spatial proteomics using BANDLE

  2022cites this paper
• Heavy-Tailed Density Estimation

  2022cites this paper
• Noise Estimation in Gaussian Process Regression

  2022influential citation
• Computationally efficient mechanism discovery for cell invasion with uncertainty quantification

  2022cites this paper
• Scalable marginalization of latent variables for correlated data

  2022cites this paper
• Challenges and Opportunities for Bayesian Statistics in Proteomics

  2022cites this paper
• Approximate reference priors for Gaussian random fields

  2022cites this paper
• Regularized Aggregation of One-Off Probability Predictions

  2022cites this paper
• Scalable Marginalization of Correlated Latent Variables with Applications to Learning Particle Interaction Kernels

  2022cites this paper
• Inferring differential subcellular localisation in comparative spatial proteomics using BANDLE

  2021cites this paper
• Variable Selection Using Nearest Neighbor Gaussian Processes

  2021cites this paper
• A Gaussian Process Emulator Based Approach for Bayesian Calibration of a Functional Input

  2021cites this paper
• Propriety of the reference posterior distribution in Gaussian process modeling

  2021influential citation
• Shifted log loss Gaussian process model for expected quality loss prediction in robust parameter design

  2021cites this paper
• Approximate Bayesian conditional copulas

  2021influential citation
• Evolutionary Gaussian Processes

  2021cites this paper
• A statistics-guided approach to dimensional quality characterization of free-form surfaces with an application to 3D printing

  2020cites this paper
• Uncertainty Quantification for complex computer models with nonstationary output: Bayesian optimal design for iterative refocussing

  2020cites this paper
• Gaussian Orthogonal Latent Factor Processes for Large Incomplete Matrices of Correlated Data

  2020cites this paper
• A Bayesian semi-parametric model for thermal proteome profiling

  2020cites this paper
• Multiple-target robust design with multiple functional outputs

  2020influential citation
• Objective Bayesian analysis for spatial Student-t regression models

  2020cites this paper
• Semi-Supervised Non-Parametric Bayesian Modelling of Spatial Proteomics.

  2019cites this paper
• Objective Bayesian Analysis of a Cokriging Model for Hierarchical Multifidelity Codes

  2019cites this paper
• Robust additive Gaussian process models using reference priors and cut-off-designs

  2019cites this paper
• Retrieving fields from proton radiography without source profiles.

  2019cites this paper
• Gaussian Process Modeling of Finite Element Models with Functional Inputs

  2019cites this paper
• Bayesian inference and non-linear extensions of the CIRCE method for quantifying the uncertainty of closure relationships integrated into thermal-hydraulic system codes

  2019cites this paper
• Bayes Linear Emulation of Simulator Networks.

  2019cites this paper
• Stochastic Methods for Emulation, Calibration and Reliability Analysis of Engineering Models

  2018cites this paper
• A frequency-calibrated Bayesian search for new particles

  2018cites this paper
• Design and analysis of computer experiments : assessing and advancing the state of the art

  2018cites this paper
• Jointly Robust Prior for Gaussian Stochastic Process in Emulation, Calibration and Variable Selection

  2018influential citation
• Nonparametric estimation of utility functions.

  2018influential citation
• A Comprehensive Bayesian Treatment of the Universal Kriging model with Matérn correlation kernels

  2018cites this paper
• Propriety of the reference posterior distribution in Gaussian Process regression

  2018cites this paper
• Objective Bayesian analysis of Kriging models with anisotropic correlation kernel

  2018cites this paper
• Probabilistic first ply failure prediction of composite laminates using a multi-scale M-SaF and Bayesian inference approach

  2018cites this paper
• Introduction to Computer Experiments

  2018cites this paper
• Calibration and prediction of two nested computer codes

  2017cites this paper
• On Uncertainty Quantification for Systems of Computer Models

  2017cites this paper
• Robust Gaussian stochastic process emulation

  2017influential citation
• Gibbs Reference Posterior for Robust Gaussian Process Emulation

  2017cites this paper
• Optimal compromise between incompatible conditional probability distributions, with application to Objective Bayesian Kriging

  2017cites this paper
• A Dynamic BI–Orthogonal Field Equation Approach to Efficient Bayesian Inversion

  2017cites this paper
• Efficient sequential experimental design for surrogate modeling of nested codes

  2017cites this paper
• Scaled Gaussian Stochastic Process for Computer Model Calibration and Prediction

  2017cites this paper
• An improved approach to Bayesian computer model calibration and prediction

  2017cites this paper
• Bayesian Model Selection for the Validation of Computer Codes

  2016cites this paper
• Robust Uncertainty Quantification and Scalable Computation for Computer Models with Massive Output

  2016influential citation
• Probabilistic First Ply Failure Analysis of Wind Turbine Blade Laminates

  2016cites this paper
• Parallel partial Gaussian process emulation for computer models with massive output

  2016cites this paper
• Fatigue life prediction of laminated composites using a multi-scale M-LaF and Bayesian inference

  2016cites this paper
• Optimization under probabilistic constraints of com- plex structures: application to the anchoring of floating offshore wind turbines

  2016cites this paper
• High fidelity micromechanics-based statistical analysis of composite material properties

  2016cites this paper
• Transitional annealed adaptive slice sampling for Gaussian process hyper-parameter estimation

  2015cites this paper
• PROBABILISTIC QUANTIFICATION OF HAZARDS: A METHODOLOGY USING SMALL ENSEMBLES OF PHYSICS-BASED SIMULATIONS AND STATISTICAL SURROGATES

  2015cites this paper
• Interpretable Priors for Hyperparameters for Gaussian Random Fields

  2015cites this paper
• Constructing Priors that Penalize the Complexity of Gaussian Random Fields

  2015cites this paper
• Sequential search strategies based on kriging

  2015cites this paper
• Spatial Interpolation of Sulfate Concentration in Groundwater Including Covariates Using Bayesian Hierarchical Models

  2015cites this paper
• Approximation of multidimensional dependences according to structured samples

  2015cites this paper
• Automating Emulator Construction for Geophysical Hazard Maps

  2014cites this paper
• Evaluation of image registration spatial accuracy using a Bayesian hierarchical model

  2014cites this paper
• Objective Bayesian analysis for autoregressive models with nugget effects

  2014cites this paper
• Objective Bayesian Analysis of Geometrically Anisotropic Spatial Data

  2013influential citation
• Objective Bayesian analysis of SAR models

  2013cites this paper
• Objective Bayesian Analysis of Geometrically Anisotropic Spatial Data

  2013cites this paper
• Calibration of Computer Simulator with Non-Gaussian Prior using Dynamically Bi-orthogonal Field Equations

  2013cites this paper
• Finding Parameters for Computer Model

  2013cites this paper
• Monotone Function Estimation for Computer Experiments

  2013cites this paper
• Gaussian process models

  2013cites this paper
• Objective Bayesian analysis of spatial models with separable correlation functions

  2013influential citation
• Objective Bayesian analysis for CAR models

  2013cites this paper
• Software Reliability Modeling with Software Metrics Data via Gaussian Processes

  2013cites this paper
• A Dynamic Bi-orthogonal Field Equation Approach for Efficient Bayesian Calibration of Large-Scale Systems

  2012cites this paper
• Objective Bayesian analysis for a spatial model with nugget effects

  2012influential citation
• Objective Bayesian analysis for the normal compositional model

  2012cites this paper
• Some advances in Bayesian spatial prediction and sampling design

  2012cites this paper
• Objective Bayesian analysis of spatial data with uncertain nugget and range parameters

  2012influential citation
• Sequential Design of Experiments to Estimate a Probability of Failure.

  2012cites this paper
• A Generalized Polynomial Chaos-Based Method for Efficient Bayesian Calibration of Uncertain Computational Models

  2012cites this paper
• Posterior Exploration for Computationally Intensive Forward Models

  2011cites this paper
• Fixed-domain asymptotics of the maximum likelihood estimator and the Gaussian process approach for deterministic models

  2011cites this paper
• Development and Implementation of Bayesian Computer Model Emulators

  2011influential citation
• Bayesian spatial modeling and interpolation using copulas

  2011cites this paper
• Functional Uniform Priors for Nonlinear Modeling

  2011cites this paper